可见/近红外光谱结合GWO-SVM对千禧番茄的分类鉴别

千禧番茄营养丰富且酸甜可口,不同千禧番茄品种的风味和营养价值均有明显差异,尤其是番茄红素、柠檬酸、维生素C和氨基酸含量的差异较大。传统人工分类方式效率低、主观性强、误检率高等问题亟待解决。为筛选综合营养价值高且风味佳的千禧番茄品种,实现千禧番茄快速准确分类,提出了基于千禧番茄光谱特征的分类模型构建及GWO优化SVM算法研究,以期解决千禧番茄自动化分类问题。以四个品种千禧番茄作为研究对象,试验样本240个,将其按2∶1比例划分为训练集160个和测试集80个样本,利用可见-近红外光谱采集系统获取350～1 000 nm范围内的千禧番茄反射强度,经光谱校正得样本反射率;为增强信噪比,截取481.15～800.03 nm范围内的光谱波段作为有效波段。由于数据采集过程受无关信息干扰影响建模效果,故将平滑点数设置为3进行Savitzky-Golay(SG)平滑预处理。预处理后采用连续投影算法(SPA)提取特征波长变量,优选得到11个特征波长反射率作为输入矩阵X,预设样本变量1, 2, 3和4作为输出矩阵Y,利用支持向量机(SVM)建立SPA-SVM千禧番茄定性分类模型,训练集和测试集平均分类准确率...     

基于灰色微分方程的传染病预测

本文归纳总结了传染病的几类预测方法,并通过一个例子,将灰色模型和微分方程模型结合,用于传染病的预测.     

基于模糊数学和灰色理论的多层次综合评价方法及其应用

针对多层次指标体系的综合评价问题,在模糊综合评判方法的基础上,结合灰色理论,提出了一种新的定量综合评价方法—多层次模糊灰关联聚类分析综合评价方法.应用该方法对油气钻井技术进行综合评价,取得了满意的结果.     

The use of grey relational analysis to determine laser cutting parameters for QFN packages with multiple performance characteristics

This paper reports an application of the grey relational analysis (GRA) to directly optimize laser cutting of a quad flat non-lead (QFN) strip using six performance characteristics. The most important performance characteristics include the cutting depth, the width of heat affected zone (HAZ), and the width of cutting line for both epoxy and Cu+epoxy materials along the cutting path. During the GRA, higher grades are obtained from any of the deeper (more complete) cutting depth, reduced widths of the HAZ and reduced widths of the cutting line. From nine experiments based on the orthogonal array of L9(3⁴), a current of 29 A, a frequency of 2 kHz, and a cutting speed of 2 mm/s were found to be the best parameters for laser cutting of a QFN strip with a thickness of 0.9 mm. Moreover, the analysis of variance (ANOVA) is also employed to determine the contribution of each control parameter on the cutting quality characteristics. The three largest measured contributions on the cutting quality in decreasing order are the frequency, the current, and the cutting speed. Compared with the Taguchi optimization method, the GRA approach is significantly simpler because it directly assigns appropriate weighting factors to the required qualities. Finally, confirmation experiments are performed to ensure the robustness of the GRA predicted optimal configuration for laser cutting a QFN strip.     

Growth of Ga-doped ZnO films with ZnO buffer layer by sputtering at room temperature

Gallium-doped zinc oxide films have been grown on glass substrates with and without ZnO buffer layers by r.f. magnetron sputtering at room temperature. In this approach, the grey relational Taguchi method analysis is adopted to solve the coating process with multiple deposition qualities. Optimal coating parameters can then be determined by using the gray relational grade as a performance index. The GZO coating parameters (r.f. power, sputtering pressure, O₂/(Ar+O₂) flow-rate ratios, and deposition time) are optimized, by taking into account the multiple performance characteristics (structural, morphological, deposition rate, electrical resistivity, and optical transmittance). The results indicate that with the grey relational Taguchi method, the electrical resistivity of GZO films is reduced from 9.23×10⁻³ to 5.77×10⁻³ Ω cm and optical transmittance increases from 79.42% to 82.95%, respectively. The ZnO buffer layer can reduce the electrical resistivity of GZO films from 5.77×10⁻³ to 2.38×10⁻³ Ω cm. It can be anticipated that room temperature deposition enables film deposition onto polymeric substrates for flexible optoelectronic devices.     

灰色关联分析结合色度法评价不同产地黄连质量

为了建立黄连色度测量方法并分析其与有效成分含量之间的相关性,应用灰色关联分析（GRA）与主成分分析（PCA）对不同产地黄连药材进行质量评价。收集了来自15个不同产区黄连药材,依据国际照明委员会CIE L*a*b*数字化系统,采用分光测色计测定15批黄连药材色度值,采用高效液相色谱（HPLC）测定表小檗碱、黄连碱、巴马汀和盐酸小檗碱4种生物碱含量,并运用SPSS 23.0软件对色度与生物碱含量进行相关性分析。将黄连药材中生物碱类成分含量、药材水分、灰分、浸出物含量及色度值作为考察指标,采用GRA法构建黄连质量评价模型并采用SIMCA-P 14.1软件进行PCA及正交偏最小二乘法分析;结果表明,色度测量方法准确可靠;相关性分析结果显示,黄连色度L^* 、a^* 、b^* 、E_ab^* （总色度值）值与表小檗碱、黄连碱、巴马汀和盐酸小檗碱的含量均有显著相关性。GRA分析结果显示,产地为重庆市的黄连与最优参考序列的相对关联度最高、质量最优;PCA分析结果显示产地为陕西省铜川市的黄连对主成分贡献率较高。GRA与色度测定所建立的黄连质量评价模型可作为黄连药材质量评价的参考依据。     

Discrete grey forecasting model and its optimization

Although the grey forecasting model has been successfully adopted in various fields and demonstrated promising results, the literatures show its performance could be further improved. For this purpose, this paper proposes a novel discrete grey forecasting model termed DGM model and a series of optimized models of DGM. This paper modifies the algorithm of GM(1, 1) model to enhance the tendency catching ability. The relationship between the two models and the forecasting precision of DGM model based on the pure index sequence is discussed. And further studies on three basic forms and three optimized forms of DGM model are also discussed. As shown in the results, the proposed model and its optimized models can increase the prediction accuracy. When the system is stable approximately, DGM model and the optimized models can effectively predict the developing system. This work contributes significantly to improve grey forecasting theory and proposes more novel grey forecasting models.     

工程环境效应引起上海地面沉降预测

地面沉降是目前常见的地质灾害之一,其长期的积累给城市带来巨大的经济损失,成为制约城市发展的主要因素。进入20世纪90年代以来,工程环境效应诱发的沉降已经成为上海地面沉降的新趋势,对于外荷载引起的地面沉降过程而言,影响因素较多,既无法用明确的数学关系式表达,又非“黑箱”那样内部结构、参数和特征一无所知,因此可将灰色预测理论应用于地面沉降的预测。针对监测和观测时间的非等时性,本文应用非等时距灰色理论模型对上海陆家嘴地区某高层建筑的沉降进行预测,并和实际监测沉降量进行了比较;对室内模型试验进行沉降预测,并和实验观测数据以及自适应神经网络系统(ANFIS)预测结果进行了比较。研究发现,对于工程环境效应引起的地面沉降,应用非等时距灰色理论模型进行沉降预测是可行、精确的。     

加权函数组合预测边坡变形模型的研究

边坡变形监测是边坡监测的主要内容之一,其变形预测问题是边坡工程中主要技术难题之一。考虑边坡位移变形预测模型的局限性,如神经网络预测方法需要大量的实测数据作为学习样本,灰色系统模型要求原始数据序列必须满足指数规律,且数据序列变化速度不能太快等。建立了边坡变形反向传播神经网络预测模型,同时给出了灰色GM(1,1)边坡预测模型。提出边坡的神经网络与灰色系统加权函数组合预测模型,采用动态规划解法,将原模型转化为多阶段决策问题,使组合预测误差的平方和最小,得到组合权重,这样得到的变形预测结果的精度将大大提高,弥补了单一方法的局限性,满足工程预测的需要。通过边坡实例加以验证,加权函数组合预测模型的预测结果精度有一定提高,能够与实际监测数据相吻合,达到准确预测的目的。     

“灰色”分析体系的定性定量分析

已知组成范围的“灰色”分析体系的校正,其首要步骤是鉴定出体系中实际存在的物种.本文对由所有可能存在组分的标准光谱与样品光谱构成的矩阵进行了奇异值分解,根据对应奇异向量的元素判断样品的组成,继而做定量分析.计算机模拟与实际分析表明方法令人满意.